academic-literature-search
Skill0 starsChanged 22 days agoMITView on GitHub
通过公开、只读学术数据库查找论文和题录元数据;仅在用户明确要求找论文、检索 Crossref/PubMed/arXiv/OpenAlex/Semantic Scholar、构造数据库检索式,或按 DOI/PMID/arXiv ID 查询记录时使用。
2 other projects use a version of this.
Adopted by
Most recently taken up by
- InternLM/WildClawBenchtheir own version, first seen Oct 8, 2026
- wu-yc/LabClawtheir own version, first seen Oct 8, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- wu-yc/LabClaw★ 1.1ksame name
- InternLM/WildClawBench★ 535same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- asreview-screening-v3Skill
- causal-inference-analysisSkill
- citation-analysisSkill
- citation-managementSkill
- dryad-data-fetcherSkill
- literature-evidence-checkerSkill
- literature-reviewSkill
- meta-analysisSkill
- paper-review-reviserSkill
- publication-integrity-checkSkill
- qualitative-research-analysisSkill
- research-ethics-consentSkill
- research-prose-naturalizerSkill
- research-reproducibility-auditorSkill
- research-source-acquisitionSkill
- research-workflowSkill
- scientific-critical-thinkingSkill
- scientific-paper-readingSkill
- scientific-translationSkill
- scientific-writingSkill
- survey-and-psychometricsSkill
The file
Files
学术文献检索
从公开学术数据库发现论文并返回可追溯的题录信息。允许自动调用,但只限明确的论文发现、数据库检索、检索式设计或标识符查找。
不要因普通网页搜索、文献综述写作、引用真实性核验、主张—来源核查、引文库整理、已有论文修改或统计分析而自动调用:跨研究综述交给 literature-review,引用与主张核验交给 literature-evidence-checker,引文库整理交给 citation-management,普通网页资料交给 web-tool-router。
数据源选择
按任务选最小充分来源,不固定要求每次查询所有数据库:
- DOI、期刊题录、出版商、基金信息:Crossref;
- 生物医学、MeSH、PMID:PubMed;
- 物理、数学、计算机及相关预印本:arXiv;
- 跨学科发现、开放获取、机构与引用关系:OpenAlex;
- 相关论文、引用/参考文献网络:Semantic Scholar。
来源覆盖和局限见 references/source-routing.md。若用户要求系统或范围综述,由 literature-review 先确定协议、来源覆盖和检索日志;本 Skill 只负责实际检索与题录返回。
执行
- 明确主题或标识符、学科范围、年份、文献类型、语言和结果数量。不会改变方向的缺省项可以说明假设后继续。
- 将概念拆成同义词和受控词;需要可复现检索时,保留数据库、完整检索式、过滤条件、查询时间、命中数及实际取得范围。
- 普通查询优先使用 PowerShell 7+ 运行
scripts/search_academic.ps1。它只向五个已列明的公开官方接口发送查询词或标识符,并把标准化 JSON 输出到终端,不安装依赖、不读取账号、不读写用户文件。 - 脚本不支持的高级过滤可以直接调用对应官方只读接口,但不要转向收费 API、登录态数据库或未审计脚本。网络失败最多重试一次;限流后停止或改用另一项适合的公开来源。
- 返回结果时保留来源、检索时间、稳定标识符和记录 URL。去重前不要把同一研究的预印本、会议版和期刊版计算成多项独立证据。
示例:
pwsh -File scripts/search_academic.ps1 -Source crossref -Query "causal inference education" -Limit 10
pwsh -File scripts/search_academic.ps1 -Source pubmed -Query "diabetes mellitus[mh] AND randomized controlled trial[pt]" -Limit 10
pwsh -File scripts/search_academic.ps1 -Source arxiv -Identifier "1706.03762"
pwsh -File scripts/search_academic.ps1 -Source openalex -Query "urban heat mortality" -Limit 10
pwsh -File scripts/search_academic.ps1 -Source semantic-scholar -Identifier "DOI:10.1038/nature12373"证据与隐私边界
- 数据库返回的是发现或题录证据,不等于论文结论已经核验;标题和摘要不等于全文。
- DOI/PMID/arXiv ID 能解析只证明记录存在,不证明元数据完全正确、论文未更正/撤回或用户的主张受支持。
- 引用量必须标注数据库和检索日期;不同平台覆盖不同,引用量不是研究质量、因果强度或纳入标准。
- 不虚构搜索结果、作者、标题、标识符、摘要、命中数或全文内容。缺失字段保持缺失。
- 查询词会发送给所选公共服务。不要发送未发表稿件全文、个人信息、受限数据或机密项目描述;必要时只使用最少、去敏的主题词。
- 不自动下载 PDF、绕过付费墙、登录账户、申请 API 密钥、保存检索、创建提醒、上传文件或写入 Zotero。需要这些动作时另行确认。
更详细的证据状态和交付字段见 references/evidence-boundaries.md。
交付
简要报告实际查询的来源与时间、检索式、过滤条件、取得数量、结果清单、可能重复/版本关系和覆盖局限。若只执行探索性查询,明确写“探索性检索”,不要声称检索全面或系统综述已经完成。
来源说明
本 Skill 以 ScienceClaw 的同名 MIT Skill 为起点进行了实质性重做:移除 PubMed MCP、内嵌 Python 引用格式化、固定 GB/T 7714 工作流和宽泛触发,改为五个公开接口的独立 PowerShell 检索器,并重新划分检索、综述、引文管理、证据核验和全文获取边界。详见 来源与改造说明,上游许可证见 LICENSE.md。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

